ARIME-DWA: Robot Path Planning Utilizing Advanced RIME Optimization and Dynamic Windows Approach

To overcome the limitations of insufficient optimization ability and the propensity to get stuck in local optima in the standard RIME algorithm for global path planning, an advanced RIME algorithm integrating the Artemisinin Optimization (AO) algorithm is proposed (ARIME). Moreover, by integrating ARIME with the strengthened Dynamic Windows Approach (DWA), the ARIME-DWA algorithm is formed, which addresses the issue of the RIME algorithm’s lack of capability for dynamic path planning. Firstly, during the population initialization stage, the good-point set strategy is employed to ensure a uniform overall distribution of the ARIME’s initial population; in the soft rime search strategy of ARIME, by integrating the comprehensive elimination mechanism of the AO, the ARIME’s global search capability is boosted; in the hard rime puncturing mechanism of ARIME, the local clearing strategy of the AO is incorporated to boost the capabilities to get away from local optima; finally, the dynamic reverse learning strategy is adopted to strengthen the diversity of population. Theoretical analysis has proven that the time complexity of the ARIME is the same as that of the RIME algorithm. To validate the performance of the ARIME, global path planning simulation experiments are conducted adopting the ARIME and six comparative algorithms. Experimental results demonstrate that ARIME outperforms other six algorithms with more robust path planning capabilities. Among them, the average path lengths solved by the ARIME are reduced by 7.7%, 24.5%, and 26.9%, respectively. Finally, local path planning experiments with the ARIME-DWA reveal its effectiveness in dynamic local path planning.